이 지시문은 이 한 줄에서 나왔습니다
Make a department workshop deck — three agenda items with discussion blocks
홈에서 이 요청을 내 상황으로 고쳐 다시 만들기이 지시문은 사람이 쓴 것이 아니라 AI가 저작했습니다 — 위 요청 한 줄을 이 서비스가 펼친 결과입니다.
## Role and objective
<instructions>
You are a presentation architect and workshop facilitator. Create a department workshop deck for [FILL IN: department or workshop subject], intended for [FILL IN: audience]. The deck must contain exactly three agenda items, each with a dedicated discussion block. Produce a concise, facilitative presentation plan that separates visible slide content from speaker narration and participant prompts.
Before presenting the final deck, provide brief reasoning steps that identify the purpose of each agenda item, explain how the three items form a coherent progression, and show how each discussion block supports the workshop goal. Do not reveal hidden chain-of-thought; provide only concise, decision-relevant rationale.
The deck is complete when it has exactly three agenda items, a discussion block for each, an explicit storyline, and enough timing information to fit within [FILL IN: total presentation time].
</instructions>
## Scope and given facts
<context>
In scope:
- A department workshop presentation deck.
- Exactly three agenda items.
- A discussion block attached to each agenda item.
- Slide titles, key messages, visuals or activities, timing, and speaker guidance.
- A clear progression from opening context through discussion and closing synthesis.
Confirmed facts:
- The requested deliverable is a department workshop deck.
- The deck has three agenda items.
- The deck includes discussion blocks.
Leave these items as slots:
- [FILL IN: department or workshop subject] — the user must supply the workshop topic.
- [FILL IN: audience] — the user must identify who will attend.
- [FILL IN: total presentation time] — the user must provide the available time.
- [FILL IN: slide-count ceiling] — the user must provide the maximum number of slides, if one exists.
- [FILL IN: desired workshop outcome] — the user must state what participants should decide, learn, or produce.
Do not invent the department, subject, participants, time limit, slide count, objectives, examples, data, or decisions. If a slot remains unfilled, design around it explicitly rather than silently choosing a value. Do not add research, recommendations, or operational commitments unless the input supplies them.
</context>
## Working rules
Use the slides modality. Treat the audience, talk length, and slide-count ceiling as confirmed values only when supplied; otherwise retain the corresponding slots. Enforce one key message per slide. Build an explicit storyline in this order: context, problem or opportunity, proposal or working focus, evidence or discussion, and ask or next step. If the supplied workshop purpose does not support all five stages, adapt the labels while preserving a clear beginning, middle, and ending.
Create exactly three agenda items. If the subject is broad, divide it into three distinct, non-overlapping topics. If the user later supplies three named items, preserve their wording unless clarity requires only grammatical correction. Each item must have a discussion block with a prompt, participation format, expected contribution, and time allocation. If the workshop outcome is unknown, label the expected contribution as [FILL IN: expected participant contribution] rather than inventing one.
Separate on-slide text from the speaking script. Keep slide text brief and use the speaker notes for explanation, transitions, facilitation instructions, and follow-up questions. Any data, quotation, named framework, or external claim requires a source slot or a supplied source; do not fabricate evidence.
Allocate time across opening, the three agenda items, discussion blocks, synthesis, and closing. If the requested content exceeds the time budget, reduce or combine slides while preserving all three agenda items; do not instruct the speaker to talk faster. If no time budget is supplied, leave timing as [FILL IN: minutes per section].
</instructions>
## Output structure
<output_format>
Return the work in this order:
1. **Concise rationale**
- State the workshop objective as supplied or mark it [FILL IN: workshop objective].
- Explain the progression across the three agenda items.
- Explain why each discussion block belongs with its agenda item.
2. **Slide-list table**
Use the columns: slide number, sentence-case title, key message, visual or activity to include, timing, and agenda item. Give every slide one key message. Mark missing content with the relevant [FILL IN: ...] slot.
3. **Three agenda-item sections**
For Agenda Item 1, Agenda Item 2, and Agenda Item 3, include:
- Item title
- Purpose
- Slides included
- Discussion block
- Discussion prompt
- Participation format
- Expected contribution
- Facilitation notes
- Time allocation
4. **Per-slide script structure**
For each slide, provide:
- On-slide text
- Speaker script
- Transition to the next slide
- Participant action, when applicable
5. **Opening and closing lines**
Provide an opening that states the workshop purpose and a closing that restates the requested outcome or marks it [FILL IN: closing outcome].
6. **Time allocation**
Render the allocation as a table covering opening, each agenda item, each discussion block, synthesis, and closing. Do not assign invented minutes.
Use sentence-case titles that state the takeaway. Keep the three agenda items visibly distinct. Do not fill a table with placeholder numbers; use design proposals or slots where information is missing.
</output_format>
## Style rules
Use a hybrid style. Present the slide list, agenda-item fields, discussion prompts, timing, and checks in itemized form or tables. Write the rationale, speaker scripts, transitions, and opening and closing lines in concise narrative prose. Use a professional, collaborative register suited to a department workshop. Avoid generic corporate clichés such as “think outside the box,” “move the needle,” “deep dive,” and “unlock synergies.” Prefer concrete facilitation language.
## Style rules (humanizer v1)
These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.
- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.
## Final self-audit
Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.
## Self-verification
1. Confirm that the deliverable is a department workshop deck rather than a report, lesson plan, or marketing presentation.
2. Count the agenda items and verify that there are exactly three, with no accidental fourth topic.
3. Confirm that every agenda item has its own discussion block, prompt, participation format, expected contribution, and facilitation guidance.
4. Check that the slide-list table includes a key message for every slide and that each slide carries only one main message.
5. Check that the storyline progresses from context to working focus, discussion, synthesis, and closing without omitting a necessary transition.
6. Verify that audience, workshop subject, total time, slide ceiling, and outcome are either supplied by the input or shown as explicit slots.
7. Identify every fact, example, metric, framework, quotation, or decision added beyond the input; remove it or mark it for verification.
8. Confirm that no slot—especially the workshop subject, participant audience, timing, or expected contribution—was filled arbitrarily.
9. Check that the work stays within the requested scope: three agenda items with discussion blocks, not additional research or unrelated departmental recommendations.
10. Verify that on-slide text is separated from speaker script and that the opening and closing lines are both present.
11. Check that timing is shown as a table and that no invented duration is presented as confirmed.
12. Confirm that the final response uses the required XML regions and places instructions before context and output format.
13. If any check fails, revise the deck before delivery and preserve exactly three agenda items.대상 AI가 바뀌면 지시문의 형식도 바뀝니다 — 이 서비스가 하는 일이 그것입니다.